diff --git a/unsloth/models/llama.py b/unsloth/models/llama.py index d1d5f5e16e..cafec19cb6 100644 --- a/unsloth/models/llama.py +++ b/unsloth/models/llama.py @@ -946,7 +946,6 @@ def LlamaModel_fast_forward_inference( else: attention_mask = None pass - print(attention_mask) next_decoder_cache = []